Claude Mythos PreviewvsGPT-5.4 Pro
Across 3 shared benchmarks, Claude Mythos Preview leads overall: Claude Mythos Preview wins 2, GPT-5.4 Pro wins 1, with 0 ties and an average score difference of +0.60.
Claude Mythos Preview
Anthropic · 2026-04-07 · Chat model
GPT-5.4 Pro
OpenAI · 2026-03-05 · Multimodal model
Claude Mythos Preview2 wins(67%)(33%)1 winGPT-5.4 Pro
Benchmark scores
Grouped by capability, sorted by largest gap within each. 3 shared benchmarks.
General Knowledge
Claude Mythos Preview 2/2| Benchmark | Claude Mythos Preview | GPT-5.4 Pro | Diff |
|---|---|---|---|
| HLE | 64.701 / 157Extended (with tools) | 58.703 / 157Thinking High (With Tools) | +6 |
| GPQA Diamond | 94.601 / 178Extended (no tools) | 94.402 / 178Thinking High (No Tools) | +0.20 |
AI Agent - Information Search
GPT-5.4 Pro 1/1| Benchmark | Claude Mythos Preview | GPT-5.4 Pro | Diff |
|---|---|---|---|
| BrowseComp | 84.904 / 45Extended (with tools) | 89.302 / 45Thinking High (With Tools) | -4.40 |
Specs
| Field | Claude Mythos Preview | GPT-5.4 Pro |
|---|---|---|
| Publisher | Anthropic | OpenAI |
| Release date | 2026-04-07 | 2026-03-05 |
| Model type | Chat model | Multimodal model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | Not available | 1M |
| Max output | 8K | 125K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Claude Mythos Preview | GPT-5.4 Pro |
|---|---|---|
| Text input | $25 / 1M tokens | $30 / 1M tokens |
| Text output | $125 / 1M tokens | $180 / 1M tokens |
Summary
- Claude Mythos Previewleads in:General Knowledge (2/2)
- GPT-5.4 Proleads in:AI Agent - Information Search (1/1)
On average across the 3 shared benchmarks, Claude Mythos Preview scores 0.60 higher.
Largest single-benchmark gap: HLE — Claude Mythos Preview 64.70 vs GPT-5.4 Pro 58.70 (+6).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.